Musical instrument classification using higher order spectra and MFCC

Higher order statistics in signal processing plays very important role to extract additional information from signals than second order statistics. This paper used higher order spectra to obtain phase entropy, non-linearity and non-gaussianity statistics from musical instrument signals to classify them hierarchically with two different taxonomies. 19 western musical instruments with full pitch range have been used for classification. Classification accuracy shows improved result when higher order spectra features are combined with MFCC.